Assignment 1

Task 1

# load packages
library(tidyverse)
library(RColorBrewer)
library(lubridate)
library(gganimate) 
library(ggimage)

# read in datasets 

agencies <- read_csv("agencies.csv")
launches <- read_csv("launches.csv")

# Make launch data frame with country, launch year, and number of launches per year for the graph with top 4 countries and the rest as "other"

launch_1 <- launches %>% 
  mutate(country = fct_collapse(state_code,
                                "Russia/USSR" = c("RU", "SU"),  
                                "United States" = "US",
                                "China" = "CN",
                                "France" = "F"),
         country = fct_lump(country, 4)) %>%  
  group_by(country, launch_year) %>% 
  count() 

# Want to find the percent of success per country to use for dot size in gganimate 
# make a dataframe with percent success per country 

launch_2 <- launches %>% 
  select(state_code, category) %>% 
  mutate(country = fct_collapse(state_code,
                                "Russia/USSR" = c("RU", "SU"),  
                                "United States" = "US",
                                "China" = "CN",
                                "France" = "F"),
         country = fct_lump(country, 4)) %>% 
    group_by(country, category) %>% 
  count()

# number of successes per country from the counts in launch_2: C-289, F-284, USSR-3024, US-1585, Other-202

# use that dataframe to calculate the percent of successful launches by country 

#first make a dataframe that just has total number of launches by country 

launch_success <- launches %>% 
  mutate(country = fct_collapse(state_code,
                                "Russia/USSR" = c("RU", "SU"),  
                                "United States" = "US",
                                "China" = "CN",
                                "France" = "F"),
         country = fct_lump(country, 4)) %>% 
    group_by(country) %>% 
  count()

# add a column for number of successes using values found from counts in launch_2 dataframe 

launch_success$number_success <- c(289, 284, 3024, 1585, 202)

# final dataframe that finds the percentage of success 

success <- launch_success %>% 
  mutate(percent = number_success/n) %>% 
  select(country, percent)

# join data frames for final graph 

launch_data <- left_join(launch_1,success, by="country")

# Read in rocket image for gganimate 

rocket <- "rocket.png"

# Graph for year vs. counts by country, color = percent of successes per country 

launch_graph <- ggplot(launch_data, aes(x=launch_year, y = n, group=country, color=percent)) +
  geom_line() +
  geom_image(aes(image = rocket)) +
  scale_y_continuous(expand = c(0,0), limits = c(0,120), breaks = seq(0,120, by = 15)) +
  scale_x_continuous(expand = c(0,0), limits = c(1955, 2020), breaks = seq(1955,2020, by=5)) +
  labs(x="Launch Year", y = "Number of Launches") +
  scale_color_distiller(palette = "YlGnBu", direction = 1, 
                        name = "Percent of Successful\nLaunches by Country") +
  theme_classic() +
  geom_text(aes(label= country, color = percent), position = position_nudge(y = 0.04, x = 9), 
            size = 5) +
  transition_reveal(country, launch_year)

## Warning: Ignoring unknown parameters: image_colour

launch_graph

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).

## Warning: Removed 5 rows containing missing values (geom_text).